⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

dp-chapter-summary

@skyfiredao⭐ 77 stars

Use when generating a plain-text chapter summary (≤150 Chinese characters + character end-of-chapter state snapshot) from the finished chapter, for cross-chapter continuity

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐⭐ 77 on GitHubGitHub ↗

Growing

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

Dreampowers

中文文档

A complete AI skill set for Chinese novel writing, built on the oh-my-openagent framework. 14 specialized skills covering every stage of fiction creation, from story ideation to manuscript completion, with core innovations in preventing worldbuilding info-dumps, reader-perspective testing, and AI-flavor elimination.

What It Does

Dreampowers provides a disciplined, skill-driven workflow for writing Chinese fiction with AI. Instead of dumping all worldbuilding details into chapter one, it enforces gradual reveal through quantified rules and multi-stage review.

  • 14 specialized skills covering the full fiction writing lifecycle
  • Three-stage review for every chapter (plot, reveal check, prose)
  • External review loop: reader + consistency review after three-stage pass, up to 3 iterations with TBD fallback for human review
  • Six Iron Rules preventing info-dumps with zero-tolerance enforcement
  • Foreshadowing tracking of setup/payoff across the entire manuscript
  • Scene-type directing with sub-modes for action, emotional, and dialogue scenes
  • Four continuous writing modes: per-chapter confirmation, batch N chapters, pause-at-volume-break, full-auto
  • Narrative timeline techniques: sequential/reverse/interpolated/supplementary with POV selection rules
  • Description methodology: camera-language system integrated into scene directing
  • External content import: bring in existing world set, character cards, outlines, and handwritten chapters
  • Mid-story outline revision: 7-step freeze-and-revise workflow for course corrections
  • Reader-perspective testing: cold-read simulation scoring page-turning desire, cognitive load, empathy, and pacing feel
  • AI-flavor detection: quantified pattern matching to eliminate formulaic AI writing habits
  • Writing style definition: 7-dimension questionnaire (narrative distance, sentence rhythm, sensory density, vocabulary register, metaphor strategy, emotional expression, dialogue ratio) with 54+ reference authors across 9 genres
  • Opt-in mature content: adult scene writing with sensory completeness and narrative integrity framework, two-tier system (softcore/hardcore), user-defined adult.md preferences, installed separately via --all flag
  • Three-layer isolation from coding skills (entry switching + dp- prefix + directory isolation)
  • Git-based version management for manuscripts

Skill Overview

Set Skills (Setup Phase)

SkillPurpose
dp-using-dreampowersEntry skill: mode switching, skill routing, workflow overview
dp-tool-researchStory premise brainstorming, one-line story summary formula, story naming, platform comparison, internet-assisted worldbuilding research, author tuning
dp-set-styleWork-level writing style definition via 7-dimension questionnaire, style reference library (54+ authors across 9 genres), generates style.md voice profile
dp-set-conceptWorld/character set with iceberg annotations (50%+ underwater), concept isolation via file-level physical separation, story-level timeline construction, external content import
dp-set-outlineVolume/chapter structure, 4 models, 6 iron rules with concept budget, foreshadowing tracking, theme weaving, narrative timeline techniques, POV rules, mid-story outline revision

Chapter Skills (Writing Phase)

SkillPurpose
dp-chapter-draftChapter writing with pre-draft gate, 3-stage review, 4 continuous writing modes, timeline execution, handwritten chapter integration, era-accurate writing (period-correct objects and perspective), outline-as-framework discipline
dp-chapter-summaryPlain-text chapter summary (≤150 chars + character end-of-chapter state snapshot, no formatting) from docs/dreampowers/release/chapter-NNN.md (falls back to chapter-NNN-TBD.md with [TBD] prefix), for cross-chapter continuity. Also detects downstream spec.md staleness on regeneration and inserts STALE-DEP markers
dp-chapter-directScene-type directing (action/emotional/dialogue sub-modes) + narrative pacing control, tension-relief law, camera-language description methodology
dp-chapter-adultOpt-in: Adult scene writing with sensory completeness, narrative integrity framework, two-tier system (softcore/hardcore), user-defined adult.md preferences

Tool Skills

SkillPurpose
dp-character-styleCharacter voice profiles, name-cover test, dialogue rules, subtext crafting
dp-tool-versionGit-based version management: structured commits, rollback, diff comparison

Review Skills

SkillPurpose
dp-review-readerReader-perspective experience testing: page-turning desire, cognitive load, empathy verification, pacing feel
dp-review-consistencyCross-chapter consistency verification (9 dimensions) + revision suggestions and AI-flavor detection/elimination
dp-review-final-reportFull-book final report: global consistency scan across all released chapters against worldbuilding, characters, outline, and timeline (human-triggered, post-completion)

Key Innovations

Lore Reveal Pacing (dp-set-outline)

Six Iron Rules enforced with zero tolerance:

  1. Mystery first, answers later
  2. Sensory experience before rules explanation
  3. Deepen existing concepts before introducing new ones
  4. Ch.1 max 3 new concepts (can be 0), subsequent max 2/chapter (can be 0)
  5. All world info through character action/dialogue only
  6. Reveal only what serves the current conflict

Foreshadowing Tracking

Individual Markdown files in docs/dreampowers/tracking/ (prefixed with thread-) tracking all foreshadowing threads with:

  • Thread recovery pacing determined by outline planning, verified by consistency review
  • Claremont Coefficient (CC = planted - resolved), warning at CC > 2
  • Overdue thread detection

Concept Isolation (dp-set-concept)

Physical file-level isolation preventing AI from seeing future worldbuilding concepts or character states:

  • One concept per file in docs/dreampowers/set/concept/
  • One character per file or directory in docs/dreampowers/set/character/
  • Chapter folders (docs/dreampowers/chapters/chapter-NNN/) as fully self-contained writing units
  • Chapter folders contain: symlinks to concepts/characters/foreshadowing threads + spec.md (7-section chapter spec: outline-stage framework §1-5 + Pre-Draft Gate evaluation §6 + self-contained writing blueprint §7)
  • Iron rules symlinked from docs/dreampowers/tracking/iron-rules.md into each chapter folder
  • Previous chapter summaries symlinked (all prior chapters) for continuity
  • Pre-Draft Gate reads all chapter folder materials, distills them into spec.md §6-7, user confirms, then writing reads only spec.md
  • Serial chapter writing: chapters must be written one at a time, in order

Three-Stage Chapter Review

Every chapter passes through three sequential review stages:

  1. Plot Review: Conflict progression, character consistency, outline adherence
  2. Reveal Check: Zero-tolerance info-dump detection against the 6 Iron Rules
  3. Prose Review: Style consistency, dialogue voice, sensory detail, rhythm

External Review Loop

After passing the three-stage review, every chapter enters an external review loop:

  1. Reader review (dp-review-reader): cold-reader experience testing across four dimensions
  2. Consistency review (dp-review-consistency): nine-dimension consistency check + revision suggestions with AI-flavor detection + writing style verification against style.md
  3. Fix and repeat: issues from both reports are merged and fixed, then the loop repeats (max 3 iterations)
  4. TBD fallback: if issues persist after 3 iterations, the release file is saved as chapter-NNN-TBD.md for human review

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • skills/dp-chapter-summary/SKILL.md8.8 KBdec1e40b95b4upstream ↗
    ---
    name: dp-chapter-summary
    description: Use when generating a plain-text chapter summary (≤150 Chinese characters + character end-of-chapter state snapshot) from the finished chapter, for cross-chapter continuity
    ---
    
    <SUBAGENT-STOP>
    如果你是被派遣执行特定任务的子代理,跳过此技能。
    </SUBAGENT-STOP>
    
    # 章节摘要生成
    
    本技能是**刚性技能**。严格遵循,不得变通。
    
    **编号稳定性契约**:本文件步骤编号使用「主步骤 + 续」结构(第一至第六步为主步骤,第四步续/第五步续为附加步骤)。**第六步「为下一章创建摘要符号链接」被 dp-chapter-draft 阶段 A 步骤 5 硬引用**。修改编号前必须同步更新所有跨文件引用。
    
    ## 定义
    
    摘要 = **全文的高度缩写**。去掉修饰,只保留事件骨架和关键细节(关键物品、关键事件、关键态度转变)。不含对话。一段纯文本,150 字以内,无任何格式。
    
    摘要之后追加一行**角色章末状态快照**,记录本章结束时各出场角色的关键状态(物理状态、情绪状态、所在位置)。状态快照以 `[章末状态]` 开头,不计入 150 字限制。
    
    它是跨章节连续性的唯一桥梁。未来章节的工作区通过软链接引用前序摘要,AI 在写作时只能看到这些摘要,看不到完整的前序章节正文。角色章末状态快照确保下一章能正确延续角色的伤势、情绪、位置等动态信息。
    
    **原则:只记录发生了什么,不透露即将发生什么。不引用大纲。不含对话。**
    
    ## 适用时机
    
    - `dp-chapter-draft` 完成一章后自动调用
    - 用户导入手写章节后,需要为其生成摘要
    - 用户要求重新生成某章摘要(如章节经过大幅修订)
    
    ## 输入与输出
    
    ### 唯一输入
    
    **章节正文** —— 按以下顺序查找:
    
    1. `docs/dreampowers/release/chapter-NNN.md`(正式终稿,优先)
    2. `docs/dreampowers/release/chapter-NNN-TBD.md`(外部审阅闭环 3 次未通过的待人工审阅稿,fallback)
    
    两者都不存在则中止执行,报告"章节尚未定稿,无法生成摘要"。
    
    **TBD 摘要标记**:从 `chapter-NNN-TBD.md` 生成的摘要必须在文件开头加一行 `[TBD] 本章未通过外部审阅,摘要可能不准`。后续章节的 spec.md §7 嵌入此摘要时会带上 TBD 前缀,草稿预审阶段 B 呈现给用户时须明示"前章未定稿"。
    
    **摘要生成阶段**(第一步到第五步)不读取 spec.md、thread-*.md、前序摘要、大纲、或任何其他文件。唯一的输入就是章节正文本身。
    
    **副作用步骤**(第五步续陈旧检测 + 第六步下一章符号链接)在摘要保存后执行,允许:
    - 遍历 `docs/dreampowers/chapters/` 目录寻找下游章节
    - 在下游章节的 `spec.md` 开头插入 STALE-DEP 标记
    - 在下一章文件夹创建 `summary-*.md` 符号链接
    
    这些副作用不影响摘要内容本身,权限已在 `dp-using-dreampowers` 的围栏例外中显式声明。
    
    ### 输出
    
    `docs/dreampowers/timeline/summary-NNN.md` —— 纯文本文件,格式要求见上方定义。
    
    ## 生成流程
    
    ### 第一步:通读章节
    
    读完整章正文。不读其他文件。
    
    ### 第二步:压缩
    
    从章节中提取事件骨架:谁(who)在哪里(where)什么时候(when)做了什么(what)、怎么做的(how)。标注关键细节:改变故事走向的物品、事件、态度转变。忽略修饰性描写、对话内容、情绪表达和章节定位词。
    
    ### 第三步:写成一段话
    
    把剩下的事实用最短的句子串成一段连贯的纯文本。
    
    ### 第四步:检查字数和格式
    
    - 超过 150 字?继续删减,直到 150 字以内。
    - 含有 `#`、`-`、`*`、`>`、`|`、`##`、`###`、`**`、`__` 等任何 Markdown 标记?去掉。
    - 含有标题行、列表、表格、分隔线?去掉。
    - 分了多段?合并为一段。
    
    ### 第四步续:生成角色章末状态快照
    
    回顾章节正文结尾处各出场角色的状态,生成一行状态快照:
    
    - 以 `[章末状态]` 开头
    - 格式:`角色名:物理状态/情绪状态/位置`,多角色用分号分隔
    - 只记录本章有实质出场的角色(被提及但未出场的不记)
    - 物理状态:健康、轻伤、重伤、昏迷、死亡等
    - 情绪状态:用一两个词概括(如 愤怒、绝望、平静、困惑)
    - 位置:当前所在地点
    - 如果某项状态本章未涉及或无变化,可省略该项
    - 状态快照不计入 150 字限制
    
    ### 第五步:保存
    
    将纯文本保存到 `docs/dreampowers/timeline/summary-NNN.md`。文件内容就是那一段话,不加任何标题行、元数据或装饰。
    
    ### 第五步续:检测下游 spec 陈旧
    
    **触发条件**:保存前 `docs/dreampowers/timeline/summary-NNN.md` 已存在(即本次是覆盖式重生成,而非首次生成)。
    
    若触发:
    
    1. 遍历 `docs/dreampowers/chapters/chapter-MMM/` 目录,找出所有 MMM > NNN 的章节文件夹
    2. 对每个存在 `spec.md` 且第六节或第七节非空的下游章节,在 spec.md 文件开头**插入陈旧标记**(`<NNN>` 为被覆盖摘要的三位数章节号,`<YYYY-MM-DD>` 为覆盖日期):
    
       ```
       <!-- STALE-DEP:summary-<NNN> 已于 <YYYY-MM-DD> 重新生成,本 spec §6/§7 中嵌入的第 <NNN> 章内容可能过时。写作前必须重跑草稿预审阶段 A,刷新后手动删除本标记。 -->
       ```
    
    3. 若同一个 spec.md 已经有相同 `<NNN>` 的 STALE-DEP 标记,仅更新日期,不重复插入
    4. 完成后向用户输出汇总:`已在以下章节的 spec.md 插入陈旧标记:chapter-MMM, chapter-MMM+1, ...`
    
    **首次生成**(timeline/summary-NNN.md 之前不存在)不触发本步。
    
    ### 第六步:为下一章创建摘要符号链接
    
    保存摘要后,检查下一章的章节文件夹(`docs/dreampowers/chapters/chapter-{NNN+1}/`)是否已存在。若已存在:
    
    1. 将 `docs/dreampowers/timeline/` 下所有已存在的 `summary-*.md` 文件,在下一章的章节文件夹内创建符号链接:`summary-NNN.md → ../../timeline/summary-NNN.md`
    2. 如果链接已存在则跳过,不重复创建
    
    若下一章的章节文件夹尚不存在,跳过此步。`dp-chapter-draft` 的草稿预审阶段会在写作前检查并补建缺失的摘要链接。
    
    ## 摘要文件格式
    
    文件内容**仅包含一段纯文本 + 角色章末状态快照**,示例:
    
    ```
    张三在废弃矿井底部发现刻有未知文字的石碑,触碰后右手出现灼烧纹路并蔓延至手腕。李四追踪到矿井入口,在外围设下监视。王五得知矿区封锁的消息后连夜出发。石碑文字与王五在古书中见过的符号一致。张三仍困在矿井中。
    
    [章末状态] 张三:重伤·右手灼烧纹路蔓延/恐惧/矿井底部; 李四:健康/警觉/矿井入口外围; 王五:健康/焦急/赶往矿区途中
    ```
    
    **注意:事件段落没有标题行,没有 `# 第 NNN 章摘要`,没有任何 Markdown 格式。事件段落就是一段话。状态快照与事件段落之间空一行,以 `[章末状态]` 开头。**
    
    ## 导入章节处理
    
    用户导入手写章节时,先存入 `docs/dreampowers/release/chapter-NNN.md`,再按标准流程生成摘要。
    
    流程与 AI 起草的章节完全相同。
    
    ## 与其他技能的交互
    
    | 关系 | 技能 | 说明 |
    |------|------|------|
    | 被调用 | `dp-chapter-draft` | 每章完成后调用本技能生成摘要 |
    | 下游 | `dp-chapter-draft` | 本技能创建摘要后,为下一章文件夹创建摘要符号链接;`dp-chapter-draft` 草稿预审时检查并补建缺失链接 |
    | 被引用 | `dp-set-outline` | 大纲中的章节计划可参考已有摘要 |
    | 被引用 | `dp-review-consistency` | 连续性检查时使用摘要核对跨章节一致性 |
    | 被引用 | `dp-review-reader` | 读者视角测试时参考已读章节的累积信息 |
    
    ## 反模式
    
    - **引用大纲的计划信息** ❌ 摘要只记录已发生的事
    - **读取 spec.md、thread-*.md 等非章节正文的文件** ❌ 唯一输入是章节正文
    - **超过 150 字** ❌ 硬限,无例外
    - **使用任何 Markdown 格式**(标题、列表、加粗、表格)❌ 纯文本,一段话
    - **分成多段** ❌ 一段话
    - **接近全章复述** ❌ 只留事实框架
    - **包含作者评价或修改建议** ❌ 事实记录,不是审查报告
    - **摘要中出现角色对话或引语** ❌ 摘要是事件骨架的缩写,不是场景复述
    - **文件开头加 `# 第 NNN 章摘要` 标题** ❌ 文件内容就是一段话,无标题
    
    ## 终止状态
    
    摘要文件已保存到 `docs/dreampowers/timeline/summary-NNN.md`。文件内容是一段纯文本(150 字以内,只含关键事实),后接一行角色章末状态快照(`[章末状态]` 开头,记录各出场角色的物理/情绪/位置状态)。若下一章文件夹已存在,所有已有摘要的符号链接已创建在下一章文件夹中。
    
  • README.mdupstream ↗

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/skyfiredao-dreampowers-skills-dp-chapter-summary.md

// REPO STATS

77 stars